Architecture

Tern has two parts: a web app and a local CLI.

app.tern.sh

The web application where you create migrations, organize tasks, chat with AI to plan, review search results, select files to process, monitor workflow execution, and analyze results. All your migration metadata lives here.

Tern CLI

A lightweight local agent that runs on your machine. It proxies LLM calls (your API keys stay local, never sent to our servers), accesses your repos (reads codebase, runs searches, makes changes), executes workflows (orchestrates AI tasks across files), and caches results locally. The CLI connects to app.tern.sh through a secure channel. Your code never leaves your machine.

Why This Split?

Security - Your code and API keys stay on your infrastructure. Collaboration - Multiple team members see the plan and results in app.tern.sh while running workflows on their own machines. Performance - Search and transformation happen locally, using your machine’s resources.

Getting Started

Install the CLI and connect it to your repos:

curl -fsSL https://tern.sh/install.sh | bash
tern connect

See Installation for details.